E-TSL: A Continuous Educational Turkish Sign Language Dataset with Baseline Methods

arXiv:2405.02984v1 Announce Type: cross
Abstract: This study introduces the continuous Educational Turkish Sign Language (E-TSL) dataset, collected from online Turkish language lessons for 5th, 6th, and 8th grades. The dataset comprises 1,410 videos totaling nearly 24 hours and includes performances from 11 signers. Turkish, an agglutinative language, poses unique challenges for sign language translation, particularly with a vocabulary where 64% are singleton words and 85% are rare words, appearing less than five times. We developed two baseline models to address …

abstract arxiv continuous cs.cl cs.cv cs.lg dataset educational grades language performances study type unique videos